相关论文: Task Agnostic Representation Consolidation: a Self…

In this paper, we propose a novel unsupervised clustering approach exploiting the hidden information that is indirectly introduced through a pseudo classification objective. Specifically, we randomly assign a pseudo parent-class label to…

Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples,…

In this work, we evaluate the effectiveness of representation learning approaches for decision making in visually complex environments. Representation learning is essential for effective reinforcement learning (RL) from high-dimensional…

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…

Continual learning aims to emulate the human ability to continually accumulate knowledge over sequential tasks. The main challenge is to maintain performance on previously learned tasks after learning new tasks, i.e., to avoid catastrophic…

Continual Learning research typically focuses on tackling the phenomenon of catastrophic forgetting in neural networks. Catastrophic forgetting is associated with an abrupt loss of knowledge previously learned by a model when the task, or…

High dimensional data analysis for exploration and discovery includes three fundamental tasks: dimensionality reduction, clustering, and visualization. When the three associated tasks are done separately, as is often the case thus far,…

Self-supervised learning approach like contrastive learning is attached great attention in natural language processing. It uses pairs of training data augmentations to build a classification task for an encoder with well representation…

Adapting Automatic Speech Recognition (ASR) models to new domains results in a deterioration of performance on the original domain(s), a phenomenon called Catastrophic Forgetting (CF). Even monolingual ASR models cannot be extended to new…

Current reinforcement learning (RL) in robotics often experiences difficulty in generalizing to new downstream tasks due to the innate task-specific training paradigm. To alleviate it, unsupervised RL, a framework that pre-trains the agent…

Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence. While recent approaches achieve some degree of CL in deep neural networks, they either (1) grow…

This paper focuses on an under-explored yet important problem: Federated Class-Continual Learning (FCCL), where new classes are dynamically added in federated learning. Existing FCCL works suffer from various limitations, such as requiring…

Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. In this work, we focus on continual text classification under the class-incremental setting. Recent CL studies…

Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentations per instance (more than two) improve generalization in…

Intelligent systems deployed in the real world suffer from catastrophic forgetting when exposed to a sequence of tasks. Humans, on the other hand, acquire, consolidate, and transfer knowledge between tasks that rarely interfere with the…

Real-world data often exhibits long tail distributions with heavy class imbalance, where the majority classes can dominate the training process and alter the decision boundaries of the minority classes. Recently, researchers have…

We present the problem of inverse constraint learning (ICL), which recovers constraints from demonstrations to autonomously reproduce constrained skills in new scenarios. However, ICL suffers from an ill-posed nature, leading to inaccurate…

Medical image segmentation has been significantly advanced by deep learning (DL) techniques, though the data scarcity inherent in medical applications poses a great challenge to DL-based segmentation methods. Self-supervised learning offers…

Deep Learning models have shown remarkable performance in a broad range of vision tasks. However, they are often vulnerable against domain shifts at test-time. Test-time training (TTT) methods have been developed in an attempt to mitigate…

Causal Temporal Representation Learning (Ctrl) methods aim to identify the temporal causal dynamics of complex nonstationary temporal sequences. Despite the success of existing Ctrl methods, they require either directly observing the domain…